{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LJP2EZDOUKAUYCWKGQC23A5ZQH","short_pith_number":"pith:LJP2EZDO","canonical_record":{"source":{"id":"2310.09971","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T22:20:39Z","cross_cats_sorted":[],"title_canon_sha256":"10d8c5311b08b907ae445a306e6bd68357043d0d045ce164f5a662fead920462","abstract_canon_sha256":"a1d97eeb62fbb564eaa81ec590ec6979d03805ec50127f19e9c1f07b76e41e5a"},"schema_version":"1.0"},"canonical_sha256":"5a5fa2646ea2814c0aca3405ad83b981f46522190f2e294a82eb5684a2caeaf5","source":{"kind":"arxiv","id":"2310.09971","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09971","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09971v4","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09971","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"LJP2EZDOUKAU","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"LJP2EZDOUKAUYCWK","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"LJP2EZDO","created_at":"2026-07-05T07:40:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LJP2EZDOUKAUYCWKGQC23A5ZQH","target":"record","payload":{"canonical_record":{"source":{"id":"2310.09971","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T22:20:39Z","cross_cats_sorted":[],"title_canon_sha256":"10d8c5311b08b907ae445a306e6bd68357043d0d045ce164f5a662fead920462","abstract_canon_sha256":"a1d97eeb62fbb564eaa81ec590ec6979d03805ec50127f19e9c1f07b76e41e5a"},"schema_version":"1.0"},"canonical_sha256":"5a5fa2646ea2814c0aca3405ad83b981f46522190f2e294a82eb5684a2caeaf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:02.797432Z","signature_b64":"k4OM8wQJUsyJ7GexVbkT4ehyh/M1AeGP7RRvYbOt1abHAPHRXu6pc6egdi1K2v5Xr7MVPW4Mip4iw3wgZjgiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a5fa2646ea2814c0aca3405ad83b981f46522190f2e294a82eb5684a2caeaf5","last_reissued_at":"2026-07-05T07:40:02.796999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:02.796999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.09971","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZMGgxGluDOdLI5TFvUpHjZV68G++HpqIIqRlgtU+GonRJ1FEkrlxopCiHMSE5iMzmibv15K3P+vFkCpWm/1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:47:23.421154Z"},"content_sha256":"247aceabcb54b5c59d8286d06311575549544a6923e2718a2161d41f360010a0","schema_version":"1.0","event_id":"sha256:247aceabcb54b5c59d8286d06311575549544a6923e2718a2161d41f360010a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LJP2EZDOUKAUYCWKGQC23A5ZQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jake Grigsby, Linxi Fan, Yuke Zhu","submitted_at":"2023-10-15T22:20:39Z","abstract_excerpt":"We introduce AMAGO, an in-context Reinforcement Learning (RL) agent that uses sequence models to tackle the challenges of generalization, long-term memory, and meta-learning. Recent works have shown that off-policy learning can make in-context RL with recurrent policies viable. Nonetheless, these approaches require extensive tuning and limit scalability by creating key bottlenecks in agents' memory capacity, planning horizon, and model size. AMAGO revisits and redesigns the off-policy in-context approach to successfully train long-sequence Transformers over entire rollouts in parallel with end"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09971","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.09971/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvAbmPwtzGb1ZO+OdnIKFA72tBXUMFArKxPKB+cVKk6y3UHYefkolY3PvCPrq0LDc53YST+HD2/hcpzNyiNODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:47:23.422068Z"},"content_sha256":"8e196d9d5d7baa1995ba42f689fba15b08ab4352c65545fbb7f2ffed8ab7ad55","schema_version":"1.0","event_id":"sha256:8e196d9d5d7baa1995ba42f689fba15b08ab4352c65545fbb7f2ffed8ab7ad55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH/bundle.json","state_url":"https://pith.science/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T02:47:23Z","links":{"resolver":"https://pith.science/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH","bundle":"https://pith.science/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH/bundle.json","state":"https://pith.science/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJP2EZDOUKAUYCWKGQC23A5ZQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LJP2EZDOUKAUYCWKGQC23A5ZQH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a1d97eeb62fbb564eaa81ec590ec6979d03805ec50127f19e9c1f07b76e41e5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T22:20:39Z","title_canon_sha256":"10d8c5311b08b907ae445a306e6bd68357043d0d045ce164f5a662fead920462"},"schema_version":"1.0","source":{"id":"2310.09971","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09971","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09971v4","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09971","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"LJP2EZDOUKAU","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"LJP2EZDOUKAUYCWK","created_at":"2026-07-05T07:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"LJP2EZDO","created_at":"2026-07-05T07:40:02Z"}],"graph_snapshots":[{"event_id":"sha256:8e196d9d5d7baa1995ba42f689fba15b08ab4352c65545fbb7f2ffed8ab7ad55","target":"graph","created_at":"2026-07-05T07:40:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.09971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AMAGO, an in-context Reinforcement Learning (RL) agent that uses sequence models to tackle the challenges of generalization, long-term memory, and meta-learning. Recent works have shown that off-policy learning can make in-context RL with recurrent policies viable. Nonetheless, these approaches require extensive tuning and limit scalability by creating key bottlenecks in agents' memory capacity, planning horizon, and model size. AMAGO revisits and redesigns the off-policy in-context approach to successfully train long-sequence Transformers over entire rollouts in parallel with end","authors_text":"Jake Grigsby, Linxi Fan, Yuke Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T22:20:39Z","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09971","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:247aceabcb54b5c59d8286d06311575549544a6923e2718a2161d41f360010a0","target":"record","created_at":"2026-07-05T07:40:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a1d97eeb62fbb564eaa81ec590ec6979d03805ec50127f19e9c1f07b76e41e5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T22:20:39Z","title_canon_sha256":"10d8c5311b08b907ae445a306e6bd68357043d0d045ce164f5a662fead920462"},"schema_version":"1.0","source":{"id":"2310.09971","kind":"arxiv","version":4}},"canonical_sha256":"5a5fa2646ea2814c0aca3405ad83b981f46522190f2e294a82eb5684a2caeaf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a5fa2646ea2814c0aca3405ad83b981f46522190f2e294a82eb5684a2caeaf5","first_computed_at":"2026-07-05T07:40:02.796999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:02.796999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4OM8wQJUsyJ7GexVbkT4ehyh/M1AeGP7RRvYbOt1abHAPHRXu6pc6egdi1K2v5Xr7MVPW4Mip4iw3wgZjgiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:02.797432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09971","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:247aceabcb54b5c59d8286d06311575549544a6923e2718a2161d41f360010a0","sha256:8e196d9d5d7baa1995ba42f689fba15b08ab4352c65545fbb7f2ffed8ab7ad55"],"state_sha256":"2ca7be1ba25fa350f4ed19f68d7dfbdd85aafdf2526731adbd0ccce978dd254d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y7FnxFv0nDRJyv15kf26yIzE4oI5C/I9ersF1FnjDBQSDafffFd/GWKinr6dfwEx0bY10P3QwkfHF3ueyW9iAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:47:23.430498Z","bundle_sha256":"043229222dabc37ed739b4cb8571d929531f92f20227525267b5f1a243be2a54"}}